中文
相关论文

相关论文: PMPGuard: Catching Pseudo-Matched Pairs in Remote …

200 篇论文

We present a novel learned keypoint detection method designed to maximize the number of correct matches for the task of non-rigid image correspondence. Our training framework uses true correspondences, obtained by matching annotated image…

计算机视觉与模式识别 · 计算机科学 2022-12-20 Welerson Melo , Guilherme Potje , Felipe Cadar , Renato Martins , Erickson R. Nascimento

Reliable retrieval-augmented generation (RAG) systems depend fundamentally on the retriever's ability to find relevant information. We show that neural retrievers used in RAG systems have blind spots, which we define as the failure to…

信息检索 · 计算机科学 2026-02-11 Zeinab Sadat Taghavi , Ali Modarressi , Hinrich Schutze , Andreas Marfurt

Semantic communication aims to transmit information most relevant to a task rather than raw data, offering significant gains in communication efficiency for applications such as telepresence, augmented reality, and remote sensing. Recent…

机器学习 · 计算机科学 2025-12-18 Matin Mortaheb , Erciyes Karakaya , Sennur Ulukus

In this work, based on the hybrid generalized approximate message passing (HyGAMP) algorithm, we propose the message-scheduling GAMP (MSGAMP) algorithm in order to address the problem of joint active device detection and channel estimation…

信息论 · 计算机科学 2021-06-15 R. B. Di Renna , R. C. de Lamare

Multimodal learning has been lacking principled ways of combining information from different modalities and learning a low-dimensional manifold of meaningful representations. We study multimodal learning and sensor fusion from a latent…

机器学习 · 计算机科学 2019-04-24 Lijiang Guo

In recent years, multimodal multidomain fake news detection has garnered increasing attention. Nevertheless, this direction presents two significant challenges: (1) Failure to Capture Cross-Instance Narrative Consistency: existing models…

计算与语言 · 计算机科学 2026-04-30 Yiheng Li , Weihai Lu , Hanyi Yu , Yue Wang

Remote sensing understanding inherently requires multi-resolution observation, since different targets and application tasks demand different levels of spatial detail. While low-resolution (LR) imagery enables efficient global observation,…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Zhenghao Xie , Jing Xiao , Zhenqi Wang , Kexin Ma , Liang Liao , Gui-Song Xia , Mi Wang

This paper introduces Grounded Image Text Matching with Mismatched Relation (GITM-MR), a novel visual-linguistic joint task that evaluates the relation understanding capabilities of transformer-based pre-trained models. GITM-MR requires a…

计算机视觉与模式识别 · 计算机科学 2023-08-07 Yu Wu , Yana Wei , Haozhe Wang , Yongfei Liu , Sibei Yang , Xuming He

Objects may appear at arbitrary scales in perspective images of a scene, posing a challenge for recognition systems that process images at a fixed resolution. We propose a depth-aware gating module that adaptively selects the pooling field…

计算机视觉与模式识别 · 计算机科学 2017-12-07 Shu Kong , Charless Fowlkes

Current remote-sensing interpretation models often focus on a single task such as detection, segmentation, or caption. However, the task-specific designed models are unattainable to achieve the comprehensive multi-level interpretation of…

计算机视觉与模式识别 · 计算机科学 2024-04-29 Danpei Zhao , Bo Yuan , Ziqiang Chen , Tian Li , Zhuoran Liu , Wentao Li , Yue Gao

As a common method in the field of computer vision, spatial attention mechanism has been widely used in semantic segmentation of remote sensing images due to its outstanding long-range dependency modeling capability. However, remote sensing…

图像与视频处理 · 电气工程与系统科学 2025-01-24 Xiaowen Ma , Rongrong Lian , Zhenkai Wu , Renxiang Guan , Tingfeng Hong , Mengjiao Zhao , Mengting Ma , Jiangtao Nie , Zhenhong Du , Siyang Song , Wei Zhang

Unsupervised Visible-Infrared Person Re-identification (USVI-ReID) presents a formidable challenge, which aims to match pedestrian images across visible and infrared modalities without any annotations. Recently, clustered pseudo-label…

计算机视觉与模式识别 · 计算机科学 2024-05-10 Xiangbo Yin , Jiangming Shi , Yachao Zhang , Yang Lu , Zhizhong Zhang , Yuan Xie , Yanyun Qu

In this paper, we study the problem of image-text matching. Inferring the latent semantic alignment between objects or other salient stuff (e.g. snow, sky, lawn) and the corresponding words in sentences allows to capture fine-grained…

计算机视觉与模式识别 · 计算机科学 2018-07-24 Kuang-Huei Lee , Xi Chen , Gang Hua , Houdong Hu , Xiaodong He

Artificial intelligence generative content (AIGC) has significantly impacted image generation in the field of remote sensing. However, the equally important area of remote sensing image (RSI) editing has not received sufficient attention.…

计算机视觉与模式识别 · 计算机科学 2025-07-02 Fangzhou Han , Lingyu Si , Zhizhuo Jiang , Hongwei Dong , Lamei Zhang , Yu Liu , Hao Chen , Bo Du

Text-to-video retrieval requires precise alignment between language and temporally rich audio-video signals. However, existing methods often emphasize visual cues while underutilizing audio semantics or relying on coarse fusion strategies,…

计算机视觉与模式识别 · 计算机科学 2025-11-19 Bowen Yang , Yun Cao , Chen He , Xiaosu Su

Remote sensing object detection has made significant progress, but most studies still focus on closed-set detection, limiting generalization across diverse datasets. Open-vocabulary object detection (OVD) provides a solution by leveraging…

计算机视觉与模式识别 · 计算机科学 2025-03-24 Ziyue Huang , Yongchao Feng , Shuai Yang , Ziqi Liu , Qingjie Liu , Yunhong Wang

Vision multi-layer perceptrons (MLPs) have shown promising performance in computer vision tasks, and become the main competitor of CNNs and vision Transformers. They use token-mixing layers to capture cross-token interactions, as opposed to…

计算机视觉与模式识别 · 计算机科学 2022-09-13 Zhicai Wang , Yanbin Hao , Xingyu Gao , Hao Zhang , Shuo Wang , Tingting Mu , Xiangnan He

Conventional techniques to establish dense correspondences across visually or semantically similar images focused on designing a task-specific matching prior, which is difficult to model. To overcome this, recent learning-based methods have…

计算机视觉与模式识别 · 计算机科学 2021-12-16 Sunghwan Hong , Seungryong Kim

Although deep learning has advanced remote sensing change detection (RSCD), most methods rely solely on image modality, limiting feature representation, change pattern modeling, and generalization especially under illumination and noise…

计算机视觉与模式识别 · 计算机科学 2025-09-05 Yijun Zhou , Yikui Zhai , Zilu Ying , Tingfeng Xian , Wenlve Zhou , Zhiheng Zhou , Xiaolin Tian , Xudong Jia , Hongsheng Zhang , C. L. Philip Chen

Nowadays, cross-modal retrieval plays an indispensable role to flexibly find information across different modalities of data. Effectively measuring the similarity between different modalities of data is the key of cross-modal retrieval.…

计算机视觉与模式识别 · 计算机科学 2017-08-17 Yuxin Peng , Jinwei Qi , Yuxin Yuan